Understanding Global Dynamics: Population,

Health Systems, Gender Equality

Teammates:

1. Jaynica Nunna 11697960

2. Vitesh Chalicheemala 11689328

3. Mounika Vankayalapati 11714417

4. Supriya Ravilla 11644767

Introduction

Our project centers on comprehending essential features of global dynamics which are

population trends, healthcare systems and gender equality.

We would like to reveal insights that can help individuals make decisions based on facts

as well as instigate positive changes in the society by dissecting and representing

information concerning these areas.

This project will therefore offer valuable insights into the intricate interconnections

leading to factors that shape today’s world.

Data Abstraction

Dataset:

We utilized three datasets sourced from reputable sources such as the Kaggle and one from given ten choice of

datasets.

These datasets encompassed a wide range of attributes, including population demographics, healthcare infrastructure,

innovation indices, and gender inequality metrics.

Number of Records:

The combined datasets comprised thousands of records, with each record representing a specific country or region.

The exact number varied across datasets but totaled well over a thousand records in aggregate.

Data Transformation:

Before analysis and visualization, we performed extensive data preprocessing to clean and harmonize the datasets.

This involved tasks such as handling missing values, standardizing units of measurement, and ensuring data

consistency across different sources.

Above Workflow Explanation

Data Collection: Collection of data from Kaggle, a well-liked platform for datasets used in the field of data

science.

Initial Visualization:

Using D3.js to visualize uncleaned dataset with the intention of providing a first look at its structure as well as

possible insights.

Data Cleaning:

Cleaning up the data using Python together with libraries such as Pandas and NumPy that would help deal with

missing values, outliers, inconsistencies etc.

Refined Visualization:

These new visualizations will be created using Python's Matplotlib or Seaborn based on the cleaned dataset

which are more focused on particular variables that we need.

Dashboard Creation:

A comprehensive view of analyzed information can be obtained by creating interactive dashboards and reports

through Microsoft Power BI and incorporating these refined visualizations.

Report Generation:

Detailed reports outlining what was seen in the analysis, insights gained, and conclusions made based on

visualization results and activities involved in number-crunching.

Task Abstraction

Task:

Objective:

To examine and represent some important parts of the world’s dynamics including population demographics,

health care systems and gender equality indicators.

Actions:

Data Collection: Collect relevant data sets from Kaggle on population demographics, healthcare infrastructure,

innovation indices and gender inequality indexes.

Initial Visualization: Apply D3.js to make early views of the raw data file for an overview of its structure and

insights that can be gained from it.

Data Cleaning: Clean the data set using Python programming language with libraries such as Pandas and

NumPy that can handle missing values, outliers and inconsistencies.

Refined Visualization: Use either Matplotlib or Seaborn, which are Python’s data visualization libraries to

achieve more sophisticated visualizations based on this cleaned dataset, emphasizing on specific variables of

interest.

Dashboard Creation: Make use of Microsoft Power BI suite to create interactive dashboards and reports which

include integrated refined visuals that give a holistic picture of the analysis findings.

Report Generation: Create comprehensive reports that summarize analytical findings, highlight insights gained

through visualizations as well as data analysis procedures leading to informed decision making.

Implementation using Tools:

D3.js:

Description: The unprocessed dataset’s initial representation was done using D3.js (Data-Driven Documents). It provided a means

of creating real-time graphs and charts that could be directly included in web browsers.

Usage: D3.js helped us create interactive visualizations such as bar plots, scatter plots and heatmaps to explore the raw data

structure and patterns in it.

Python:

Description: Python with libraries like Pandas, NumPy, Matplotlib and Seaborn played a key role in preprocessing, analysis and

visualization of the data.

Usage: Missing values were imputed using Pandas and Numpy during data cleaning as well as removing any outliers and

consistencies. However, cleaned datasets were then used to plot refined visualizations through Matplotlib & Seaborn which provide

insights through multiple types of charts & plots.

Microsoft Power BI:

Description: Microsoft Power BI acted as an all-inclusive platform for building interactive dashboards and reports while

integrating the use of visualizations giving a holistic view of analyzed data.

Usage: Power BI allowed us to create interactive visualizations such as bar charts, line graphs or maps for instance and then

include them in interactive dashboards without any hindrances whatsoever. Besides data modeling capabilities in Power BI

facilitated relationship building.



Results for

Analysis

Using D3

This visualization represents the

population of the top ten countries in

2023.

Each bar's height corresponds to the

population size of a specific country.

By comparing the heights of the bars,

we can see which countries have larger

populations relative to others

And data used here is not

preprocessed or cleaned.

Using D3

we're visualizing the Global Innovation

Index (GII) of the top ten countries.

Each bar represents a country, and the

height of the bar indicates its GII score.

This visualization allows us to compare

the innovation levels of different

countries, with taller bars indicating

higher innovation scores.

And data used here is not

preprocessed or cleaned.

Data Pre-processing

using python

After preprocessing datasets, we stored

all three datasets into csv., using

pandas.

Later using Visualization libraries we

created below visuals.

Relationship between

pysicians and birth

registration

In terms of healthcare systems, each point in

this scatter plot represents a nation's journey

towards wellness.

As we see the axis of physicians per 1000

people, we uncover a tale of access to

healthcare.

Meanwhile, the completeness of birth

registration whispers a story of governance

and care, painting a picture of a nation's

commitment to its citizens' well-being.

On top we have shown same visual

using D3 , that’s before data

preprocessing.

Population health

heatmap

Across the world, this map paints a

picture of people's presence.

Each color showcases the density of

population, offering a straightforward

glimpse into where people gather, from

bustling cities to quieter regions.

Gender inequality index

map

This map provides a straightforward

view of gender inequality across the

world.

Darker colors indicate higher levels

of inequality, while lighter shades

represent areas with less disparity

between genders.

It's a clear snapshot of the global

landscape of gender equality efforts.

Next we are going to

create more visual insights

using powerBI by

embedding report here.

Microsoft Power BI

•Links

•https://raw.githubusercontent.com/viteshc/SDV_5320_Project_Group-4/main/1

•https://raw.githubusercontent.com/viteshc/SDV_5320_Project_Group-4/main/2

•https://raw.githubusercontent.com/viteshc/SDV_5320_Project_Group-4/main/3

•Vizhub link:

•https://vizhub.com/JaynicaNunna/b24d5d2b720346fa9c55699098eeac8b?edit=files&fi

le=script.js&tabs=package.json%7Escript.js

•Power Bi:

•https://app.powerbi.com/links/IacAgqpw1U?ctid=70de1992-07c6-480f-a318-

a1afcba03983&pbi_source=linkShare

Work Management: Implementation Status Report

Work Completed:

Data Collection:

Description: Gathered relevant datasets from Kaggle.

Responsibility: All team members contributed to identifying and selecting datasets.

Contributions: Equal contribution from all team members.

Initial Visualization (D3.js):

Description: Created preliminary visualizations of the uncleaned dataset using D3.js.

Responsibility: Vitesh Chalicheemala

Contributions: Vitesh contributed 100% to this task.

Data Cleaning (Python):

Description: Cleaned the dataset using Python, Pandas, and NumPy.

Responsibility: Jaynica Nunna, Mounika Vankayalapati

Contributions: Jaynica and Mounika each contributed 50% to this task.

Refined Visualization (Python):

Description: Created refined visualizations based on the cleaned dataset using Python's data visualization libraries.

Responsibility: Supriya Ravilla

Contributions: Supriya contributed 100% to this task.

Work Management: Implementation Status

Report

Dashboard Creation (Microsoft Power BI):

Description: Designed interactive dashboards and reports using Microsoft Power BI.

Responsibility: All team members collaborated on dashboard design and

implementation.

Contributions: Equal contribution from all team members.

Report Generation:

Description: Created detailed reports summarizing analysis findings.

Responsibility: Jaynica Nunna

Contributions: Jaynica contributed 100% to this task.

References

1. Kaggle. (n.d.). Kaggle: Your Home for Data Science. Retrieved from

https://www.kaggle.com/

2. D3.js. (n.d.). D3.js - Data-Driven Documents. Retrieved from https://d3js.org/

3. Python Software Foundation. (n.d.). Python. Retrieved from https://www.python.org/

4. McKinney, W., Perktold, J., Seabold, S., & Wes McKinney. (2020). pandas-dev/pandas:

Pandas 1.2.4. Zenodo. https://doi.org/10.5281/zenodo.4611042

5. Hunter, J. D. (2007). Matplotlib: A 2D Graphics Environment. Computing in Science &

Engineering, 9(3), 90–95. https://doi.org/10.1109/MCSE.2007.55

6. Microsoft Corporation. (n.d.). Power BI. Retrieved from https://powerbi.microsoft.com/